Road to efficiency: Mobility-driven joint task offloading and resource utilization protocol for connected vehicle networks

Abstract

Connected Vehicle Networks (CVNs) is an emerging technology that enables vehicles to communicate with each other and with various Internet of Things (IoT) devices of the transportation infrastructure to enhance safety, efficiency, and convenience. In CVN, task offloading is a critical issue due to utilizing high resource computation and dynamic network changes. Specifically, the dynamically changing computation capacity of the vehicles in traffic, as well as the location changes due to their mobility, may cause the result of the task offloading not to return to the task origin vehicle. On the other hand, traditional fixed-position fog networks in inter-vehicle task offloading schemes are limited in terms of tracking vehicles’ status on dynamic traffic and have high utilization costs. Mobile fog computing mitigates these problems by offering efficient and responsive task-processing providing utilization of nearby connected vehicles. Besides, it extends coverage of connected vehicles to support real-time communication of these vehicles. In this paper, a mobility-driven joint task offloading and resource utilization protocol called MobTORU is proposed to optimize resource utilization and efficient task-processing in CVNs. Also, we propose a resource-efficient and task offloading algorithm called RELiOff which is employed in MobTORU protocol for CVN. The proposed protocol and algorithm are evaluated through an Intelligent Transportation System (ITS) application scenario and the experiments using a real-world dataset containing real vehicular mobility traces. Experimental results show that our proposed protocol and algorithm have 93.8% efficiency on the overall system and 99.9% efficiency on processed tasks in the resource utilization of offloaded tasks achieved, respectively. © 2024 Elsevier B.V.